Infrared and visible light image fusion method based on saliency fusion

Abstract

The invention discloses an infrared and visible light image fusion method based on saliency fusion. Three extraction methods including salient target extraction based on infrared image segmentation and Bessel background reconstruction based on a quadtree, sparse salient target extraction based on structure low-rank coding and salient target multi-scale detail extraction based on Laplace are adopted, an infrared salient target is determined, and the infrared image and the visible light image are fused, so that the visual saliency characteristic of the target is obtained, and meanwhile, the detail information of the scene is reserved. According to the image fusion method provided by the invention, the defects of the infrared image can be overcome, and the advantages of visible light and infrared light can be exerted, so that the fused image has the advantages of infrared light and visible light at the same time, and the detection and reconnaissance capability of the system is improved.

Description

technical field [0001] The invention relates to the technical field of aircraft visual navigation and imaging guidance simulation, more specifically, it relates to an infrared and visible light image fusion method based on saliency fusion. Background technique [0002] The development of information fusion technology makes it possible for multiple sensors to work together. Information fusion technology refers to the multi-level, multi-faceted, and multi-level processing and fusion of information obtained at the same scene at the same time, so as to obtain more reliable, richer, more accurate, and more meaningful information. [0003] At present, the most common is the fusion of infrared sensor and visible light sensor. Since the image captured by the visible light sensor is the reflected image of the object, the formed image conforms to the observation of the human eye. The image contains rich detailed information, but it is easily affected by the weather. In the case of sm...

AI Technical Summary

Problems solved by technology

[0003] At present, the most common is the fusion of infrared sensor and visible light sensor. Since the image captured by the visible light sensor is the reflected image of the object, the formed image conforms to the observation of the human eye. The image contains rich detailed information, but it is easily affected by the weather. A lot of scene information will be lost under smog and low illumination conditions, and it cannot work around the clock, especially when the chromaticity difference between the target and the background is small, it is easy to lose the target

The infrared image is the image produced by the radiation of the object itself, which can "actively" obtain the target information in the scene, and can well display the hidden hot target, which is less affected by the lighting conditions and bad weather, but at the same time Due to the limitations of the imaging principle, the contrast of infrared images is low, the spatial correlation is strong, and the ability to reflect target details is relatively poor. Insufficient, it can give full play to the advantages of visible light and infrared, so that the fusion image has the advantages of infrared and visible light at the same time, which is conducive to improving the detection and reconnaissance capabilities of the system

Images